from skimage.io import imread
import pyclesperanto_prototype as cle
import stackview
import napari
from skimage.measure import regionprops_table
import pandas as pd
import numpy as np
import napari_pyclesperanto_assistant._advanced_statistics as nas
from napari_clusters_plotter._dimensionality_reduction import umap
from napari_clusters_plotter._clustering import kmeans_clustering
import seaborn as sns
import matplotlib.pyplot as plt

nuclei = imread("c:/structure/data/Lund-100MB.tif")[2]

stackview.insight(nuclei)

shape (116, 636, 354) dtype uint8 size 24.9 MB min 0 max 233

viewer = napari.Viewer(ndisplay=3)

viewer.add_image(nuclei)
napari.utils.nbscreenshot(viewer, canvas_only=True)

viewer.camera.angles

(0.0, 0.0, 90.00000000000001)

viewer.camera.angles = (90, 0, 90)
viewer.camera.zoom = 2.6
napari.utils.nbscreenshot(viewer, canvas_only=True)

bg_subtracted = cle.top_hat_box(nuclei, radius_x=10, radius_y=10, radius_z=10)

labels = cle.voronoi_otsu_labeling(bg_subtracted, spot_sigma=0.5, outline_sigma=0)

viewer.add_labels(labels)
napari.utils.nbscreenshot(viewer, canvas_only=True)

neighbor_connections = cle.draw_mesh_between_proximal_labels(labels, maximum_distance=25)

viewer.add_image(neighbor_connections, opacity=0.5)
napari.utils.nbscreenshot(viewer, canvas_only=True)

neighbor_stats = cle.statistics_of_labelled_neighbors(labels, proximal_distances=[25], nearest_neighbor_ns=[], dilation_radii=[])
neighbor_stats

C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\pyclesperanto_prototype\_tier0\_opencl_execute.py:281: RuntimeWarning: overflow encountered in cast
  arguments.append(np.array([value], np.float32))

{'label': array([   1,    2,    3, ..., 2184, 2185, 2186]),
 'touching_neighbor_count': array([5., 3., 5., ..., 0., 0., 0.], dtype=float32),
 'minimum_distance_of_touching_neighbors': array([6.2099104, 4.783322 , 5.3679237, ..., 0.       , 0.       ,
        0.       ], dtype=float32),
 'average_distance_of_touching_neighbors': array([9.229854 , 5.9108377, 8.382152 , ..., 0.       , 0.       ,
        0.       ], dtype=float32),
 'maximum_distance_of_touching_neighbors': array([12.065423 ,  6.8475013, 10.020198 , ...,  0.       ,  0.       ,
         0.       ], dtype=float32),
 'max_min_distance_ratio_of_touching_neighbors': array([1.9429303, 1.4315368, 1.8666804, ...,       nan,       nan,
              nan], dtype=float32),
 'proximal_neighbor_count_d25': array([25., 18., 16., ...,  1.,  2.,  2.], dtype=float32),
 'distance_to_most_distant_other': array([427.15463, 445.42847, 466.85413, ..., 378.41937, 389.53204,
        366.03748], dtype=float32),
 'touch_portion_above_0_neighbor_count': array([5., 3., 5., ..., 0., 0., 0.], dtype=float32),
 'touch_portion_above_0.16_neighbor_count': array([1., 2., 1., ..., 0., 0., 0.], dtype=float32),
 'touch_portion_above_0.2_neighbor_count': array([1., 2., 1., ..., 0., 0., 0.], dtype=float32),
 'touch_portion_above_0.33_neighbor_count': array([0., 0., 0., ..., 0., 0., 0.], dtype=float32),
 'touch_portion_above_0.5_neighbor_count': array([0., 0., 0., ..., 0., 0., 0.], dtype=float32),
 'touch_portion_above_0.75_neighbor_count': array([0., 0., 0., ..., 0., 0., 0.], dtype=float32),
 'touch_count_sum': array([122.,  95., 227., ...,   0.,   0.,   0.], dtype=float32),
 'minimum_touch_count': array([  2.,  17.,  18., ..., 291., 291., 291.], dtype=float32),
 'maximum_touch_count': array([51., 44., 99., ...,  0.,  0.,  0.], dtype=float32),
 'minimum_touch_portion': array([0.00809717, 0.11486486, 0.03964758, ..., 0.4084507 , 0.4084507 ,
        0.4084507 ], dtype=float32),
 'maximum_touch_portion': array([0.20647773, 0.2972973 , 0.21806167, ..., 0.        , 0.        ,
        0.        ], dtype=float32),
 'standard_deviation_touch_portion': array([0.12640575, 0.0777027 , 0.12824279, ..., 0.        , 0.        ,
        0.        ], dtype=float32)}

intensity_stats = cle.statistics_of_labelled_pixels(nuclei, labels)
intensity_stats

{'label': array([   1,    2,    3, ..., 2184, 2185, 2186]),
 'original_label': array([   1,    2,    3, ..., 2184, 2185, 2186]),
 'bbox_min_x': array([ 24.,  24.,  24., ..., 337., 340., 342.], dtype=float32),
 'bbox_min_y': array([399., 421., 447., ..., 364., 295., 333.], dtype=float32),
 'bbox_min_z': array([0., 0., 0., ..., 0., 0., 0.], dtype=float32),
 'bbox_max_x': array([ 33.,  32.,  33., ..., 341., 344., 344.], dtype=float32),
 'bbox_max_y': array([407., 427., 455., ..., 371., 303., 337.], dtype=float32),
 'bbox_max_z': array([ 5.,  3., 10., ...,  4.,  6.,  1.], dtype=float32),
 'bbox_width': array([10.,  9., 10., ...,  5.,  5.,  3.], dtype=float32),
 'bbox_height': array([9., 7., 9., ..., 8., 9., 5.], dtype=float32),
 'bbox_depth': array([ 6.,  4., 11., ...,  5.,  7.,  2.], dtype=float32),
 'min_intensity': array([72., 76., 71., ..., 42., 41., 41.], dtype=float32),
 'max_intensity': array([118., 123., 118., ...,  56.,  63.,  46.], dtype=float32),
 'sum_intensity': array([23517., 10137., 36104., ...,  5469.,  9536.,   730.], dtype=float32),
 'area': array([241., 101., 405., ..., 115., 195.,  17.], dtype=float32),
 'mean_intensity': array([ 97.58091 , 100.36633 ,  89.145676, ...,  47.556522,  48.902565,
         42.941177], dtype=float32),
 'sum_intensity_times_x': array([ 683280.,  280863., 1032066., ..., 1854783., 3261392.,  250256.],
       dtype=float32),
 'mass_center_x': array([ 29.054726,  27.706718,  28.585918, ..., 339.1448  , 342.0084  ,
        342.81644 ], dtype=float32),
 'sum_intensity_times_y': array([ 9481387.,  4303452., 16278259., ...,  2011203.,  2853611.,
          244765.], dtype=float32),
 'mass_center_y': array([403.17163, 424.52914, 450.87134, ..., 367.74603, 299.24612,
        335.29453], dtype=float32),
 'sum_intensity_times_z': array([ 36878.,  10033., 175518., ...,   7696.,  22396.,    207.],
       dtype=float32),
 'mass_center_z': array([1.5681422 , 0.98974055, 4.861456  , ..., 1.4072043 , 2.348574  ,
        0.28356165], dtype=float32),
 'sum_x': array([ 6971.,  2773., 11571., ..., 39002., 66691.,  5828.], dtype=float32),
 'centroid_x': array([ 28.925312,  27.455446,  28.57037 , ..., 339.14783 , 342.00513 ,
        342.82352 ], dtype=float32),
 'sum_y': array([ 97158.,  42871., 182621., ...,  42289.,  58356.,   5700.],
       dtype=float32),
 'centroid_y': array([403.14523, 424.46533, 450.91605, ..., 367.73044, 299.26154,
        335.29413], dtype=float32),
 'sum_z': array([ 383.,  102., 1963., ...,  167.,  469.,    5.], dtype=float32),
 'centroid_z': array([1.5892116 , 1.009901  , 4.846914  , ..., 1.452174  , 2.4051282 ,
        0.29411766], dtype=float32),
 'sum_distance_to_centroid': array([ 764.4512  ,  253.58925 , 1471.8877  , ...,  281.93085 ,
         553.607   ,   23.183668], dtype=float32),
 'mean_distance_to_centroid': array([3.1719966, 2.5107846, 3.6342907, ..., 2.4515727, 2.8390102,
        1.3637452], dtype=float32),
 'sum_distance_to_mass_center': array([ 764.4398  ,  254.87625 , 1471.9258  , ...,  281.9798  ,
         553.65326 ,   23.185287], dtype=float32),
 'mean_distance_to_mass_center': array([3.1719494, 2.5235271, 3.6343846, ..., 2.4519982, 2.8392475,
        1.3638405], dtype=float32),
 'standard_deviation_intensity': array([10.205904 , 14.266017 , 11.750536 , ...,  4.137193 ,  5.784661 ,
         1.7977302], dtype=float32),
 'max_distance_to_centroid': array([6.6307807, 4.9968524, 7.272151 , ..., 4.09282  , 4.557525 ,
        2.3196287], dtype=float32),
 'max_distance_to_mass_center': array([6.7388296, 5.2128887, 7.273856 , ..., 4.091985 , 4.5413914,
        2.319256 ], dtype=float32),
 'mean_max_distance_to_centroid_ratio': array([2.0904124, 1.9901557, 2.0009823, ..., 1.6694672, 1.6053219,
        1.7009252], dtype=float32),
 'mean_max_distance_to_mass_center_ratio': array([2.1245072, 2.0657153, 2.0013998, ..., 1.668837 , 1.5995053,
        1.7005333], dtype=float32)}

table = nas.advanced_statistics(nuclei, labels)
table

C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\napari_pyclesperanto_assistant\_advanced_statistics.py:18: UserWarning: 'Statistics of labeled pixels including neighborhood statistics' is deprecated. Use 'Label statistics' instead.
  warnings.warn("'Statistics of labeled pixels including neighborhood statistics' is deprecated. Use 'Label statistics' instead.")

Measurements Completed.

	label	original_label	bbox_min_x	bbox_min_y	bbox_min_z	bbox_max_x	bbox_max_y	bbox_max_z	bbox_width	bbox_height	...	mean_distance_to_mass_center	standard_deviation_intensity	max_distance_to_centroid	max_distance_to_mass_center	mean_max_distance_to_centroid_ratio	mean_max_distance_to_mass_center_ratio	avg_distance_of_2_nearest_neigbors	avg_distance_of_3_nearest_neigbors	avg_distance_of_4_nearest_neigbors	touching_neighbor_count
0	1	1	24.0	399.0	0.0	33.0	407.0	5.0	10.0	9.0	...	3.171949	10.205904	6.630781	6.738830	2.090412	2.124507	7.590932	8.087852	8.520962	5.0
1	2	2	24.0	421.0	0.0	32.0	427.0	3.0	9.0	7.0	...	2.523527	14.266017	4.996852	5.212889	1.990156	2.065715	5.442506	5.910838	6.655530	3.0
2	3	3	24.0	447.0	0.0	33.0	455.0	10.0	10.0	9.0	...	3.634385	11.750536	7.272151	7.273856	2.000982	2.001400	6.675785	7.331525	7.972640	5.0
3	4	4	24.0	454.0	0.0	34.0	463.0	4.0	11.0	10.0	...	3.281820	9.279823	5.899060	5.854911	1.798308	1.784044	7.276857	8.062333	8.871074	4.0
4	5	5	26.0	474.0	0.0	33.0	482.0	6.0	8.0	9.0	...	3.012358	9.451112	5.345889	5.261563	1.776183	1.746659	8.528680	8.941842	10.448359	3.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2181	2182	2182	336.0	314.0	9.0	341.0	322.0	18.0	6.0	9.0	...	3.302892	5.972755	5.170120	5.152297	1.565350	1.559935	20.661205	21.193321	22.736378	0.0
2182	2183	2183	337.0	246.0	0.0	341.0	254.0	6.0	5.0	9.0	...	2.875455	5.113707	4.701997	4.726860	1.635346	1.643865	24.059181	24.953699	27.809708	0.0
2183	2184	2184	337.0	364.0	0.0	341.0	371.0	4.0	5.0	8.0	...	2.451998	4.137193	4.092820	4.091985	1.669467	1.668837	22.216997	24.679289	26.675577	0.0
2184	2185	2185	340.0	295.0	0.0	344.0	303.0	6.0	5.0	9.0	...	2.839247	5.784661	4.557525	4.541391	1.605322	1.599505	20.784912	23.756897	25.889828	0.0
2185	2186	2186	342.0	333.0	0.0	344.0	337.0	1.0	3.0	5.0	...	1.363840	1.797730	2.319629	2.319256	1.700925	1.700533	20.612461	24.629789	27.179501	0.0

2186 rows × 41 columns

table.columns

Index(['label', 'original_label', 'bbox_min_x', 'bbox_min_y', 'bbox_min_z',
       'bbox_max_x', 'bbox_max_y', 'bbox_max_z', 'bbox_width', 'bbox_height',
       'bbox_depth', 'min_intensity', 'max_intensity', 'sum_intensity', 'area',
       'mean_intensity', 'sum_intensity_times_x', 'mass_center_x',
       'sum_intensity_times_y', 'mass_center_y', 'sum_intensity_times_z',
       'mass_center_z', 'sum_x', 'centroid_x', 'sum_y', 'centroid_y', 'sum_z',
       'centroid_z', 'sum_distance_to_centroid', 'mean_distance_to_centroid',
       'sum_distance_to_mass_center', 'mean_distance_to_mass_center',
       'standard_deviation_intensity', 'max_distance_to_centroid',
       'max_distance_to_mass_center', 'mean_max_distance_to_centroid_ratio',
       'mean_max_distance_to_mass_center_ratio',
       'avg_distance_of_2_nearest_neigbors',
       'avg_distance_of_3_nearest_neigbors',
       'avg_distance_of_4_nearest_neigbors', 'touching_neighbor_count'],
      dtype='object')

table_dim_red = pd.DataFrame({k: table[k] for k in [

#'min_intensity', 
#'max_intensity', 
#'area',
'mean_intensity', 
#'mass_center_x',
#'mass_center_y', 
#'mass_center_z', 
#'centroid_x', 
#'centroid_y', 
#'centroid_z', 
#'mean_distance_to_centroid',
#'mean_distance_to_mass_center',
'standard_deviation_intensity', 
#'max_distance_to_centroid',
#'max_distance_to_mass_center', 
#'mean_max_distance_to_centroid_ratio',
#'mean_max_distance_to_mass_center_ratio',
#'avg_distance_of_2_nearest_neigbors',
#'avg_distance_of_3_nearest_neigbors',
'avg_distance_of_4_nearest_neigbors', 
'touching_neighbor_count'

]})

umap_table = umap(table_dim_red, n_neighbors=15, n_components=2, min_dist=0.1)
umap_table

C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\umap\distances.py:1063: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
  @numba.jit()
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\umap\distances.py:1071: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
  @numba.jit()
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\umap\distances.py:1086: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
  @numba.jit()
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\umap\umap_.py:660: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
  @numba.jit()

('UMAP',
 array([[ 7.2152653 ,  0.25958052],
        [ 7.1479826 ,  0.49318957],
        [ 4.948551  ,  0.11478776],
        ...,
        [-4.4583693 ,  6.3534966 ],
        [-4.556163  ,  6.0747447 ],
        [-4.2785654 ,  6.71291   ]], dtype=float32))

umap_table[1][:,1].shape

(2186,)

table_to_cluster = pd.DataFrame({
    "UMAP0":umap_table[1][:,0],
    "UMAP1":umap_table[1][:,0],    
})

clustering = kmeans_clustering(table_to_cluster, cluster_number=3, iterations=10)
clustering

C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=9.
  warnings.warn(

('KMEANS', array([2, 2, 2, ..., 0, 0, 0]))

table['kmeans_clustering'] = clustering[1]
table['UMAP0'] = umap_table[1][:,0]
table['UMAP1'] = umap_table[1][:,1]

import matplotlib.pyplot as plt
plt.style.use('dark_background')

from napari_clusters_plotter._utilities import get_nice_colormap

# Create a scatter plot of UMAP0 vs UMAP1 colored by kmeans_clustering
sns.scatterplot(data=table, x='UMAP0', y='UMAP1', hue='kmeans_clustering', palette=get_nice_colormap())

C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\AppData\Local\Temp\ipykernel_19652\1629480065.py:2: UserWarning: The palette list has more values (255) than needed (3), which may not be intended.
  sns.scatterplot(data=table, x='UMAP0', y='UMAP1', hue='kmeans_clustering', palette=get_nice_colormap())

<Axes: xlabel='UMAP0', ylabel='UMAP1'>

table.columns

Index(['label', 'original_label', 'bbox_min_x', 'bbox_min_y', 'bbox_min_z',
       'bbox_max_x', 'bbox_max_y', 'bbox_max_z', 'bbox_width', 'bbox_height',
       'bbox_depth', 'min_intensity', 'max_intensity', 'sum_intensity', 'area',
       'mean_intensity', 'sum_intensity_times_x', 'mass_center_x',
       'sum_intensity_times_y', 'mass_center_y', 'sum_intensity_times_z',
       'mass_center_z', 'sum_x', 'centroid_x', 'sum_y', 'centroid_y', 'sum_z',
       'centroid_z', 'sum_distance_to_centroid', 'mean_distance_to_centroid',
       'sum_distance_to_mass_center', 'mean_distance_to_mass_center',
       'standard_deviation_intensity', 'max_distance_to_centroid',
       'max_distance_to_mass_center', 'mean_max_distance_to_centroid_ratio',
       'mean_max_distance_to_mass_center_ratio',
       'avg_distance_of_2_nearest_neigbors',
       'avg_distance_of_3_nearest_neigbors',
       'avg_distance_of_4_nearest_neigbors', 'touching_neighbor_count',
       'kmeans_clustering', 'UMAP0', 'UMAP1'],
      dtype='object')

plt.figure(figsize=(10, 6))
sns.scatterplot(data=table, x='centroid_y', y='centroid_x', hue='kmeans_clustering', palette=get_nice_colormap())

C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\mambaforge\envs\bio39\lib\site-packages\seaborn\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if pd.api.types.is_categorical_dtype(vector):
C:\Users\haase\AppData\Local\Temp\ipykernel_19652\153530680.py:2: UserWarning: The palette list has more values (255) than needed (3), which may not be intended.
  sns.scatterplot(data=table, x='centroid_y', y='centroid_x', hue='kmeans_clustering', palette=get_nice_colormap())

<Axes: xlabel='centroid_y', ylabel='centroid_x'>

trainers = [
    "Stéphane Rigaud, Image Analysis Hub, Institut Pasteur, Paris",
    "Laura Žigutytė, Clinical AI / Kather lab, EKFZ, TU Dresden",
    "Anja Neumann, ScaDS.AI, Uni Leipzig",
    "Marie-Sophie von Braun, ScaDS.AI, Uni Leipzig",
    "Matthias Täschner, ScaDS.AI, Uni Leipzig",
    "Christian Martin, ScaDS.AI, Uni Leipzig",
    "Jan Ewald, ScaDS.AI, Uni Leipzig",
    "Robert Haase, ScaDS.AI, Uni Leipzig",
]

sorted(trainers)

['Anja Neumann, ScaDS.AI, Uni Leipzig',
 'Christian Martin, ScaDS.AI, Uni Leipzig',
 'Jan Ewald, ScaDS.AI, Uni Leipzig',
 'Laura Žigutytė, Clinical AI / Kather lab, EKFZ, TU Dresden',
 'Marie-Sophie von Braun, ScaDS.AI, Uni Leipzig',
 'Matthias Täschner, ScaDS.AI, Uni Leipzig',
 'Robert Haase, ScaDS.AI, Uni Leipzig',
 'Stéphane Rigaud, Image Analysis Hub, Institut Pasteur, Paris']